A Scientific Paper Recommendation Framework Based on Multi-Topic Communities and Modified PageRank

Abstract

Personalized PageRank is a variant of PageRank, widely developed for citation recommendation. However, the personalized PageRank that works with a vast amount and rich scholarly data still results in information overload. Sometimes, junior scholars still need help to arrange queries quickly because of limited domain knowledge. Senior researchers need reference papers regarding a similar topic they intend to search for and related topics as a new insight. In this research, scientific citation recommendation aims to find the most influential papers with similar and related topics. Related topic papers in serendipitous perspectives are reference papers that are novel, diversified and unexpected to a user. The unexpectedness of recommended papers can be papers with different topics to queries but still relevant. To accomplish these challenges, we propose a framework of scientific citation recommendation with serendipitous perspectives. The framework includes feature extraction of an academic citation network, selection of multi-topic communities, and ranking papers in the selected multi-topic communities by modified PageRank. Papers in the chosen communities tend to link to similar and related papers. Modified PageRank is an extension of personalized PageRank, which works on multi-topic communities and manuscript queries. The experiments reveal that the proposed models outperform some models of personalized PageRank and some models of Content-Based Filtering. The multi-topic communities-based models work more effectively than the baselines if they run in a large dataset since the topic communities become more cohesive.

Using an explicit query and a topic model for scientific article recommendation

“…In their most recent study, Hadhiatma et al (2023) introduced a novel approach to scientific paper recommendation that combines community detection and a modified Pag-eRank algorithm. Specifically, the authors utilized Latent Dirichlet Allocation to identify the main topics in scientific papers and to form multi-topic communities of papers.…”

A Metric Learning Perspective on the Implicit Feedback-Based Recommendation Data Imbalance Problem

“…Content-based approaches compute the text's similarity and produce a recommendation list. Typically, they use techniques like topic modeling [1], word embedding [2], word frequency analysis [3], or a combination of word and sequence modeling approaches [4]. Collaborative filtering-based approaches assess a user's reading records and predict the user's preferences for unread papers using methods such as nearest neighbor computation, matrix decomposition [5], and deep learning [6].…”